DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation

• URL: http://arxiv.org/abs/2510.10782v1
• Date: Sun, 12 Oct 2025 19:56:20 GMT
• Title: DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation
• Abstract summary: We propose a novel framework, Disentangled Style-Content GAN (DISC-GAN), which integrates style-content disentanglement with a cluster-specific training strategy towards underwater image synthesis.<n>Our framework demonstrates state-of-the-art performance, obtaining a photorealistic Structural Similarity Index (SSIM) of 0.9012, an average Peak Signal-to-Noise Ratio (PSNR) of 32.5118 dB, and a Frechet Inception Distance (FID) of 13.3728.
• Score: 4.045232231131666
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose a novel framework, Disentangled Style-Content GAN (DISC-GAN), which integrates style-content disentanglement with a cluster-specific training strategy towards photorealistic underwater image synthesis. The quality of synthetic underwater images is challenged by optical due to phenomena such as color attenuation and turbidity. These phenomena are represented by distinct stylistic variations across different waterbodies, such as changes in tint and haze. While generative models are well-suited to capture complex patterns, they often lack the ability to model the non-uniform conditions of diverse underwater environments. To address these challenges, we employ K-means clustering to partition a dataset into style-specific domains. We use separate encoders to get latent spaces for style and content; we further integrate these latent representations via Adaptive Instance Normalization (AdaIN) and decode the result to produce the final synthetic image. The model is trained independently on each style cluster to preserve domain-specific characteristics. Our framework demonstrates state-of-the-art performance, obtaining a Structural Similarity Index (SSIM) of 0.9012, an average Peak Signal-to-Noise Ratio (PSNR) of 32.5118 dB, and a Frechet Inception Distance (FID) of 13.3728.

Related papers

• HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection [52.11418741192251]
  We propose an asymmetric prompting framework that adjusts the category centers by aligning with fine-grained image cues.<n>Specifically, we introduce a single set of prompts to capture the consistent representative patterns, which serves as a unified anchor for real content.<n>While (2) for fake category, we construct sample-adaptive prompts that specialize in capturing diverse cues from different samples, enabling adaptive modeling of forgery image variations.
  arXiv  Detail & Related papers  (2026-05-26T01:20:18Z)
• DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis [63.59932602411222]
  DMAligner is a diffusion-based framework for image alignment through alignment-oriented view synthesis.<n>We propose a Dynamics-aware Diffusion Training approach for learning conditional image generation.<n>We develop the Dynamic Scene Image Alignment (DSIA) dataset using Blender, which includes 1,033 indoor and outdoor scenes with over 30K image pairs tailored for image alignment.
  arXiv  Detail & Related papers  (2026-02-26T14:00:07Z)
• Morphological Addressing of Identity Basins in Text-to-Image Diffusion Models [0.0]
  We show that morphological pressure creates navigable gradients at multiple levels of the text-to-image generative pipeline.<n>We generate 200 novel nonsense words from English sound-symbolic clusters.
  arXiv  Detail & Related papers  (2026-02-20T09:37:35Z)
• Neural Scene Designer: Self-Styled Semantic Image Manipulation [67.43125248646653]
  We introduce the Neural Scene Designer (NSD), a novel framework that enables photo-realistic manipulation of user-specified scene regions.<n>NSD ensures both semantic alignment with user intent and stylistic consistency with the surrounding environment.<n>To capture fine-grained style representations, we propose the Progressive Self-style Representational Learning (PSRL) module.
  arXiv  Detail & Related papers  (2025-09-01T11:59:03Z)
• ZePo: Zero-Shot Portrait Stylization with Faster Sampling [61.14140480095604]
  This paper presents an inversion-free portrait stylization framework based on diffusion models that accomplishes content and style feature fusion in merely four sampling steps. We propose a feature merging strategy to amalgamate redundant features in Consistency Features, thereby reducing the computational load of attention control.
  arXiv  Detail & Related papers  (2024-08-10T08:53:41Z)
• DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image Enhancement [77.0360085530701]
  Underwater image enhancement (UIE) is a challenging task due to the complex degradation caused by underwater environments. Previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features. Our approach utilizes predicted images to dynamically update pseudo-labels, adding a dynamic gradient to optimize the network's gradient space.
  arXiv  Detail & Related papers  (2023-12-12T06:07:21Z)
• Improving Few-shot Image Generation by Structural Discrimination and Textural Modulation [10.389698647141296]
  Few-shot image generation aims to produce plausible and diverse images for one category given a few images from this category. Existing approaches either globally interpolate different images or fuse local representations with pre-defined coefficients. This paper proposes a novel mechanism to inject external semantic signals into internal local representations.
  arXiv  Detail & Related papers  (2023-08-30T16:10:21Z)
• A Generalized Physical-knowledge-guided Dynamic Model for Underwater Image Enhancement [15.625794673532509]
  We design a Generalized Underwater image enhancement method via a Physical-knowledge-guided Dynamic Model (short for GUPDM) This study changes the global atmosphere light and the transmission to simulate various underwater image types. We then design ADS and TDS that use dynamic convolutions to adaptively extract prior information from underwater images and generate parameters for PMS.
  arXiv  Detail & Related papers  (2023-08-10T09:09:15Z)
• PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators [120.06891448820447]
  How to obtain clear and visually pleasant images has become a common concern of people. The task of underwater image enhancement (UIE) has also emerged as the times require. In this paper, we propose a physical model-guided GAN model for UIE, referred to as PUGAN. Our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics.
  arXiv  Detail & Related papers  (2023-06-15T07:41:12Z)
• Underwater object classification combining SAS and transferred optical-to-SAS Imagery [12.607649347048442]
  We propose a multi-modal combination to discriminate between man-made targets and objects such as rocks or litter. We offer a novel classification algorithm that overcomes the problem of intensity and object formation differences between the two modalities. Results from 7,052 pairs of SAS and optical images collected during sea experiments show improved classification performance.
  arXiv  Detail & Related papers  (2023-04-24T07:42:16Z)
• SIAN: Style-Guided Instance-Adaptive Normalization for Multi-Organ Histopathology Image Synthesis [63.845552349914186]
  We propose a style-guided instance-adaptive normalization (SIAN) to synthesize realistic color distributions and textures for different organs. The four phases work together and are integrated into a generative network to embed image semantics, style, and instance-level boundaries.
  arXiv  Detail & Related papers  (2022-09-02T16:45:46Z)
• Semantic Image Synthesis via Diffusion Models [174.24523061460704]
  Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks.<n>Recent work on semantic image synthesis mainly follows the de facto GAN-based approaches.<n>We propose a novel framework based on DDPM for semantic image synthesis.
  arXiv  Detail & Related papers  (2022-06-30T18:31:51Z)
• Domain Adaptation for Underwater Image Enhancement via Content and Style Separation [7.077978580799124]
  Underwater image suffer from color cast, low contrast and hazy effect due to light absorption, refraction and scattering. Recent learning-based methods demonstrate astonishing performance on underwater image enhancement. We propose a domain adaptation framework for underwater image enhancement via content and style separation.
  arXiv  Detail & Related papers  (2022-02-17T09:30:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.